A Fingerprint Technique for Indoor Localization using Autoencoder based Semi-supervised Deep Extreme Learning Machine
Journal article
Khatab, Z. E., Gazestani, A.H., Ghorashi, S. and Ghavami, M. (2020). A Fingerprint Technique for Indoor Localization using Autoencoder based Semi-supervised Deep Extreme Learning Machine. Signal Processing. 181, p. 107915. https://doi.org/10.1016/j.sigpro.2020.107915
Authors | Khatab, Z. E., Gazestani, A.H., Ghorashi, S. and Ghavami, M. |
---|---|
Abstract | In recent years, because of the growing demand for location based services in indoor environment and development of Wi-Fi, fingerprint-based indoor localization has attracted many researchers’ interest. In Wireless Sensor Networks (WSNs), fingerprint based localization methods estimate the target location by using a pattern matching model for the measurements of the Received Signal Strength (RSS) from the available transmitter sensors, which are collected by a smartphone with internal sensors. Due to the dynamic nature of the environment, the fingerprint database needs to be updated, periodically. Hence, it is better to add new fingerprint data to the primary database in order to update them. However, collecting the labeled data is time consuming and labor intensive. In this paper, we propose a novel algorithm, which uses high level extracted features by an autoencoder to improve the localization performance in the classification process. Furthermore, to update the fingerprint data base, we also add crowd-sourced labeled and unlabeled data in order to improve the localization performance, gradually. Simulation results indicate that the proposed method provides a significant improvement in localization performance, using high level extracted features by the autoencoder, and by increasing the number of unlabeled training data. |
Keywords | Indoor localization; Fingerprint; Wireless sensor network; Semi-supervised; Autoencoder; Deep extreme learning machine |
Year | 2020 |
Journal | Signal Processing |
Journal citation | 181, p. 107915 |
Publisher | Elsevier |
ISSN | 01651684 |
Digital Object Identifier (DOI) | https://doi.org/10.1016/j.sigpro.2020.107915 |
Publication dates | |
Online | 30 Nov 2020 |
Publication process dates | |
Deposited | 30 Nov 2020 |
Accepted | 27 Nov 2020 |
Accepted author manuscript | License File Access Level Open |
Page range | 107915 |
Permalink -
https://openresearch.lsbu.ac.uk/item/8v753
Download files
Accepted author manuscript
Final Manuscript-SIGPRO-D-18-01056R2.pdf | ||
License: CC BY-NC-ND 4.0 | ||
File access level: Open |
141
total views75
total downloads0
views this month0
downloads this month